domain-entities-review
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands including
ls,rg(grep), andgit diffto discover project configuration and search for design patterns within the local filesystem. - [COMMAND_EXECUTION]: It executes a project-local Python script (
.claude/scripts/code_graph) to perform dependency tracing and code graph analysis. - [COMMAND_EXECUTION]: The skill is authorized to invoke the
spawn_agentcapability to parallelize the review process for large changesets, using a structured prompt template to maintain protocol consistency. - [PROMPT_INJECTION]: The skill processes project source code as untrusted input, which presents a surface for indirect prompt injection. This risk is mitigated by requiring mandatory
file:lineevidence for every finding and a terminal validation gate ($why-review) that adversarialy tests findings before they are finalized.
Audit Metadata